2 citations · 5 across the 5 of their papers we have counts for
7 papers
Smoothly Giving up: Robustness for Simple Models
Tyler Sypherd, Nathan Stromberg, Richard Nock +2
There is a growing need for models that are interpretable and have reduced energy and computational cost (e.g., in health care analytics and federated learning). Examples of algori…
-GAN: Convergence and Estimation Guarantees
Gowtham R. Kurri, Monica Welfert, Tyler Sypherd +1
We prove a two-way correspondence between the min-max optimization of general CPE loss function GANs and the minimization of associated -divergences. We then focus on -GAN, d…
Being Properly Improper
Tyler Sypherd, Richard Nock, Lalitha Sankar
Properness for supervised losses stipulates that the loss function shapes the learning algorithm towards the true posterior of the data generating distribution. Unfortunately, data…
Realizing GANs via a Tunable Loss Function
Gowtham R. Kurri, Tyler Sypherd, Lalitha Sankar
We introduce a tunable GAN, called -GAN, parameterized by , which interpolates between various -GANs and Integral Probability Metric based GANs (under constr…
On the alpha-loss Landscape in the Logistic Model
Tyler Sypherd, Mario Diaz, Lalitha Sankar +1
We analyze the optimization landscape of a recently introduced tunable class of loss functions called -loss, , in the logistic model. This family encapsulates t…
A Tunable Loss Function for Robust Classification: Calibration, Landscape, and Generalization
Tyler Sypherd, Mario Diaz, John Kevin Cava +3
We introduce a tunable loss function called -loss, parameterized by , which interpolates between the exponential loss (), the log-loss (), and the…
A Tunable Loss Function for Binary Classification
Tyler Sypherd, Mario Diaz, Lalitha Sankar +1
We present -loss, , a tunable loss function for binary classification that bridges log-loss () and - loss (). We prove that -loss has a…